AI Paper Atlas

Research map / Probabilistic and scientific modeling / Differential equations and PDEs

"Hey, that’s not an ODE": Faster ODE Adjoints via Seminorms

Patrick Kidger, Ricky T. Q. Chen, Terry J Lyons

ICML 2021 · Probabilistic and scientific modeling › Differential equations and PDEs · approach: Neural ODE training and analysis · 2 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Use the adjoint seminorm instead of the default normNeural CDE · Speech Commandsbackward NFE: 14.36 ±1.09 -> 8.67 ±1.60; 30.67 ±2.48 -> 12.75 ±2.00; 77.95 ±4.47 -> 29.39 ±0.80Improved
Use the adjoint seminorm instead of the default normNeural CDE · Speech Commandstest accuracy: 92.6 ±0.4 -> 92.5 ±0.5; 92.8 ±0.4 -> 92.5 ±0.5; 92.4 ±0.7 -> 92.9 ±0.4No clear effect
Use the adjoint seminorm instead of the default normContinuous Normalizing Flow · CIFAR-10 (d_h=64)backward NFE: 41.65 ±1.97 -> 38.93 ±1.32Improved
Use the adjoint seminorm instead of the default normContinuous Normalizing Flow · MNISTbackward NFE: 41.50 ±2.35 -> 37.03 ±0.96; 44.24 ±1.78 -> 37.85 ±0.94; 48.60 ±2.30 -> 41.84 ±1.92Improved
Use the adjoint seminorm instead of the default normContinuous Normalizing Flow · CIFAR-10 and MNISTtest bits/dim: 3.3492 ±0.0059 -> 3.3428 ±0.0121; 0.9968 ±0.0020 -> 0.9942 ±0.0013; 0.9623 ±0.0020 -> 0.9603 ±0.0021; 0.9439 ±0.0030 -> Mixed
Use the adjoint seminorm instead of the default normSymplectic ODE-Net · Fully-actuated double pendulumbackward NFE: 46.45 ±0.01 -> 26.55 ±0.01Improved
Use the adjoint seminorm instead of the default normSymplectic ODE-Net · Fully-actuated double pendulumtest L2 loss: 1.247 ±0.520 -> 2.995 ±2.190Hurt
Exclude a_theta and a_t channels from step-size controlNeural differential equation adjoint solve · Neural CDE, continuous normalizing flows, and Hamiltonian dynamicsbackward function evaluations: 40% fewer function evaluations (median); as much as 62% fewer function evaluationsImproved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy